jbylund

#!/usr/bin/python
import urllib2
import json
import pprint

pp = pprint.PrettyPrinter(indent=4)

class instance_size:
  def __init__(self):
    pass

jbylund

a bunch of files named loglines_... contain pixel requests, these correspond to roughly logparse output or instance id logs in s3

joseph 11:46:33 @ hephaestus ~/loglines> /bin/grep -H -F "e=24&" loglines_* > error_pixels


To take a 60 second sample from all live nginx (requires moreutils, as well as probably discover in your path):
#!/bin/bash
parallel -j 150 -i bash -c "source ~/.bashrc; ssh {} \"timeout 60 tail -f /mnt/nginx_access.log\" > loglines_{}" -- $( discover.py nginx | cut -f 3 | sort )

Get a sorted list of top 10 i keys which threw errors:

jbylund

#!/usr/bin/python
import csv
import math
import multiprocessing
import os
import sys
import tempfile

READ_BUFFER = 2**13

jbylund

function FindProxyForURL(url, host) {
	if (
		  shExpMatch(host, "101com.com") ||
		  shExpMatch(host, "*.101com.com") ||
		  shExpMatch(host, "101order.com") ||
		  shExpMatch(host, "*.101order.com") ||
		  shExpMatch(host, "123found.com") ||
		  shExpMatch(host, "*.123found.com") ||
		  shExpMatch(host, "123pagerank.com") ||
		  shExpMatch(host, "*.123pagerank.com") ||

jbylund

#!/usr/bin/python
import subprocess
import os
import json
import sys

def get_staged_files():
  return subprocess.check_output("git diff --cached --name-only".split()).strip().split('\n')

class Check(object):

jbylund

class DateRange(object):
  start_of_time = datetime.date.min
  end_of_time = datetime.date.max
  def __init__(self, start=start_of_time, end=end_of_time):
    if type(start) != type(DateRange.start_of_time):
      self.start = datetime.datetime.strptime(start, '%Y-%m-%d').date()
    else:
      self.start = start
    if type(end) != type(DateRange.end_of_time):
      self.end = datetime.datetime.strptime(end, '%Y-%m-%d').date()

jbylund

#!/usr/bin/python
import argparse
import hashlib
import json
import multiprocessing
import os
import re
import resource
import subprocess
import urllib

jbylund

export workdir=$(mktemp -d)
(
  cd $workdir
  wget http://ftpmirror.gnu.org/parallel/parallel-latest.tar.bz2
  tar -xf parallel-latest.tar.bz2
  cd $(find . -maxdepth 1 -mindepth 1 -type d)
  ./configure
  make -j $(grep -c processor /proc/cpuinfo)
  sudo --non-interactive make install
)

jbylund

#!/usr/bin/python
"""
Something that's kind of sort of like a multiprocessing pool, but is designed for heterogenously sized tasks
"""
import math
import multiprocessing
import random
import sys
import time
import Queue

jbylund

#!/usr/bin/python
"""Get the set of instance id's (exclude spot instances)!"""
import boto3
import datetime
import json
import redis
import sys
import base64
VERSION = 0.2